* [PATCH 25/51] netfilter: nf_flow_table: fix offloading connections with SNAT+DNAT
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Pass all NAT types to the flow offload struct, otherwise parts of the
address/port pair do not get translated properly, causing connection
stalls
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 0699981a8511..eb0d1658ac05 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -84,7 +84,7 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
if (ct->status & IPS_SRC_NAT)
flow->flags |= FLOW_OFFLOAD_SNAT;
- else if (ct->status & IPS_DST_NAT)
+ if (ct->status & IPS_DST_NAT)
flow->flags |= FLOW_OFFLOAD_DNAT;
return flow;
--
2.11.0
^ permalink raw reply related
* [PATCH 24/51] netfilter: nf_flow_table: add missing condition for TCP state check
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Avoid looking at unrelated fields in UDP packets
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_ip.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 692c75ef5cb7..82451b7e0acb 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -15,11 +15,14 @@
#include <linux/tcp.h>
#include <linux/udp.h>
-static int nf_flow_tcp_state_check(struct flow_offload *flow,
- struct sk_buff *skb, unsigned int thoff)
+static int nf_flow_state_check(struct flow_offload *flow, int proto,
+ struct sk_buff *skb, unsigned int thoff)
{
struct tcphdr *tcph;
+ if (proto != IPPROTO_TCP)
+ return 0;
+
if (!pskb_may_pull(skb, thoff + sizeof(*tcph)))
return -1;
@@ -248,7 +251,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
return NF_DROP;
thoff = ip_hdr(skb)->ihl * 4;
- if (nf_flow_tcp_state_check(flow, skb, thoff))
+ if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
return NF_ACCEPT;
if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
@@ -460,7 +463,8 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
return NF_ACCEPT;
- if (nf_flow_tcp_state_check(flow, skb, sizeof(*ip6h)))
+ if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb,
+ sizeof(*ip6h)))
return NF_ACCEPT;
if (skb_try_make_writable(skb, sizeof(*ip6h)))
--
2.11.0
^ permalink raw reply related
* [PATCH 22/51] netfilter: nf_flow_table: add support for sending flows back to the slow path
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Since conntrack hasn't seen any packets from the offloaded flow in a
while, and the timeout for offloaded flows is set to an extremely long
value, we need to fix up the state before we can send a flow back to the
slow path.
For TCP, reset td_maxwin in both directions, which makes it resync its
state on the next packets.
Use the regular timeout for TCP and UDP established connections.
This allows the slow path to take over again once the offload state has
been torn down
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_core.c | 50 +++++++++++++++++++++++++++++++++++++-
1 file changed, 49 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index ff5e17a15963..0699981a8511 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -100,6 +100,43 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
}
EXPORT_SYMBOL_GPL(flow_offload_alloc);
+static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
+{
+ tcp->state = TCP_CONNTRACK_ESTABLISHED;
+ tcp->seen[0].td_maxwin = 0;
+ tcp->seen[1].td_maxwin = 0;
+}
+
+static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+{
+ const struct nf_conntrack_l4proto *l4proto;
+ struct net *net = nf_ct_net(ct);
+ unsigned int *timeouts;
+ unsigned int timeout;
+ int l4num;
+
+ l4num = nf_ct_protonum(ct);
+ if (l4num == IPPROTO_TCP)
+ flow_offload_fixup_tcp(&ct->proto.tcp);
+
+ l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), l4num);
+ if (!l4proto)
+ return;
+
+ timeouts = l4proto->get_timeouts(net);
+ if (!timeouts)
+ return;
+
+ if (l4num == IPPROTO_TCP)
+ timeout = timeouts[TCP_CONNTRACK_ESTABLISHED];
+ else if (l4num == IPPROTO_UDP)
+ timeout = timeouts[UDP_CT_REPLIED];
+ else
+ return;
+
+ ct->timeout = nfct_time_stamp + timeout;
+}
+
void flow_offload_free(struct flow_offload *flow)
{
struct flow_offload_entry *e;
@@ -107,7 +144,8 @@ void flow_offload_free(struct flow_offload *flow)
dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
e = container_of(flow, struct flow_offload_entry, flow);
- nf_ct_delete(e->ct, 0, 0);
+ if (flow->flags & FLOW_OFFLOAD_DYING)
+ nf_ct_delete(e->ct, 0, 0);
nf_ct_put(e->ct);
kfree_rcu(e, rcu_head);
}
@@ -164,6 +202,8 @@ EXPORT_SYMBOL_GPL(flow_offload_add);
static void flow_offload_del(struct nf_flowtable *flow_table,
struct flow_offload *flow)
{
+ struct flow_offload_entry *e;
+
rhashtable_remove_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
nf_flow_offload_rhash_params);
@@ -171,12 +211,20 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
nf_flow_offload_rhash_params);
+ e = container_of(flow, struct flow_offload_entry, flow);
+ clear_bit(IPS_OFFLOAD_BIT, &e->ct->status);
+
flow_offload_free(flow);
}
void flow_offload_teardown(struct flow_offload *flow)
{
+ struct flow_offload_entry *e;
+
flow->flags |= FLOW_OFFLOAD_TEARDOWN;
+
+ e = container_of(flow, struct flow_offload_entry, flow);
+ flow_offload_fixup_ct_state(e->ct);
}
EXPORT_SYMBOL_GPL(flow_offload_teardown);
--
2.11.0
^ permalink raw reply related
* [PATCH 23/51] netfilter: nf_flow_table: tear down TCP flows if RST or FIN was seen
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Allow the slow path to handle the shutdown of the connection with proper
timeouts. The packet containing RST/FIN is also sent to the slow path
and the TCP conntrack module will update its state.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_ip.c | 30 +++++++++++++++++++++++++++---
1 file changed, 27 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index dc570fb7641d..692c75ef5cb7 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -15,6 +15,23 @@
#include <linux/tcp.h>
#include <linux/udp.h>
+static int nf_flow_tcp_state_check(struct flow_offload *flow,
+ struct sk_buff *skb, unsigned int thoff)
+{
+ struct tcphdr *tcph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*tcph)))
+ return -1;
+
+ tcph = (void *)(skb_network_header(skb) + thoff);
+ if (unlikely(tcph->fin || tcph->rst)) {
+ flow_offload_teardown(flow);
+ return -1;
+ }
+
+ return 0;
+}
+
static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
__be32 addr, __be32 new_addr)
{
@@ -119,10 +136,9 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
}
static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
- enum flow_offload_tuple_dir dir)
+ unsigned int thoff, enum flow_offload_tuple_dir dir)
{
struct iphdr *iph = ip_hdr(skb);
- unsigned int thoff = iph->ihl * 4;
if (flow->flags & FLOW_OFFLOAD_SNAT &&
(nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
@@ -202,6 +218,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
struct flow_offload *flow;
struct net_device *outdev;
const struct rtable *rt;
+ unsigned int thoff;
struct iphdr *iph;
__be32 nexthop;
@@ -230,8 +247,12 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
if (skb_try_make_writable(skb, sizeof(*iph)))
return NF_DROP;
+ thoff = ip_hdr(skb)->ihl * 4;
+ if (nf_flow_tcp_state_check(flow, skb, thoff))
+ return NF_ACCEPT;
+
if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
- nf_flow_nat_ip(flow, skb, dir) < 0)
+ nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
return NF_DROP;
flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
@@ -439,6 +460,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
return NF_ACCEPT;
+ if (nf_flow_tcp_state_check(flow, skb, sizeof(*ip6h)))
+ return NF_ACCEPT;
+
if (skb_try_make_writable(skb, sizeof(*ip6h)))
return NF_DROP;
--
2.11.0
^ permalink raw reply related
* [PATCH 21/51] netfilter: nf_flow_table: in flow_offload_lookup, skip entries being deleted
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Preparation for sending flows back to the slow path
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_core.c | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 5a81e4f771e9..ff5e17a15963 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -184,8 +184,21 @@ struct flow_offload_tuple_rhash *
flow_offload_lookup(struct nf_flowtable *flow_table,
struct flow_offload_tuple *tuple)
{
- return rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
- nf_flow_offload_rhash_params);
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct flow_offload *flow;
+ int dir;
+
+ tuplehash = rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
+ nf_flow_offload_rhash_params);
+ if (!tuplehash)
+ return NULL;
+
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+ if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))
+ return NULL;
+
+ return tuplehash;
}
EXPORT_SYMBOL_GPL(flow_offload_lookup);
--
2.11.0
^ permalink raw reply related
* [PATCH 20/51] netfilter: nf_flow_table: add a new flow state for tearing down offloading
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
On cleanup, this will be treated differently from FLOW_OFFLOAD_DYING:
If FLOW_OFFLOAD_DYING is set, the connection is going away, so both the
offload state and the connection tracking entry will be deleted.
If FLOW_OFFLOAD_TEARDOWN is set, the connection remains alive, but
the offload state is torn down. This is useful for cases that require
more complex state tracking / timeout handling on TCP, or if the
connection has been idle for too long.
Support for sending flows back to the slow path will be implemented in
a following patch
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_flow_table.h | 2 ++
net/netfilter/nf_flow_table_core.c | 22 ++++++++++++++--------
2 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 5aa49524ebef..ba9fa4592f2b 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -68,6 +68,7 @@ struct flow_offload_tuple_rhash {
#define FLOW_OFFLOAD_SNAT 0x1
#define FLOW_OFFLOAD_DNAT 0x2
#define FLOW_OFFLOAD_DYING 0x4
+#define FLOW_OFFLOAD_TEARDOWN 0x8
struct flow_offload {
struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX];
@@ -103,6 +104,7 @@ void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
int nf_flow_table_init(struct nf_flowtable *flow_table);
void nf_flow_table_free(struct nf_flowtable *flow_table);
+void flow_offload_teardown(struct flow_offload *flow);
static inline void flow_offload_dead(struct flow_offload *flow)
{
flow->flags |= FLOW_OFFLOAD_DYING;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 0d38f20fd226..5a81e4f771e9 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -174,6 +174,12 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
flow_offload_free(flow);
}
+void flow_offload_teardown(struct flow_offload *flow)
+{
+ flow->flags |= FLOW_OFFLOAD_TEARDOWN;
+}
+EXPORT_SYMBOL_GPL(flow_offload_teardown);
+
struct flow_offload_tuple_rhash *
flow_offload_lookup(struct nf_flowtable *flow_table,
struct flow_offload_tuple *tuple)
@@ -226,11 +232,6 @@ static inline bool nf_flow_has_expired(const struct flow_offload *flow)
return (__s32)(flow->timeout - (u32)jiffies) <= 0;
}
-static inline bool nf_flow_is_dying(const struct flow_offload *flow)
-{
- return flow->flags & FLOW_OFFLOAD_DYING;
-}
-
static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
{
struct flow_offload_tuple_rhash *tuplehash;
@@ -258,7 +259,8 @@ static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
if (nf_flow_has_expired(flow) ||
- nf_flow_is_dying(flow))
+ (flow->flags & (FLOW_OFFLOAD_DYING |
+ FLOW_OFFLOAD_TEARDOWN)))
flow_offload_del(flow_table, flow);
}
out:
@@ -419,10 +421,14 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
{
struct net_device *dev = data;
- if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex)
+ if (!dev) {
+ flow_offload_teardown(flow);
return;
+ }
- flow_offload_dead(flow);
+ if (flow->tuplehash[0].tuple.iifidx == dev->ifindex ||
+ flow->tuplehash[1].tuple.iifidx == dev->ifindex)
+ flow_offload_dead(flow);
}
static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
--
2.11.0
^ permalink raw reply related
* [PATCH 18/51] netfilter: nf_flow_table: track flow tables in nf_flow_table directly
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Avoids having nf_flow_table depend on nftables (useful for future
iptables backport work)
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_flow_table.h | 1 +
include/net/netfilter/nf_tables.h | 3 ---
net/netfilter/nf_flow_table_core.c | 21 ++++++++++++++++++---
net/netfilter/nf_tables_api.c | 17 -----------------
4 files changed, 19 insertions(+), 23 deletions(-)
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index f876e32a60b8..ab408adba688 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -21,6 +21,7 @@ struct nf_flowtable_type {
};
struct nf_flowtable {
+ struct list_head list;
struct rhashtable rhashtable;
const struct nf_flowtable_type *type;
struct delayed_work gc_work;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index cd368d1b8cb8..2f2062ae1c45 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1109,9 +1109,6 @@ struct nft_flowtable {
struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table,
const struct nlattr *nla,
u8 genmask);
-void nft_flow_table_iterate(struct net *net,
- void (*iter)(struct nf_flowtable *flowtable, void *data),
- void *data);
void nft_register_flowtable_type(struct nf_flowtable_type *type);
void nft_unregister_flowtable_type(struct nf_flowtable_type *type);
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 09d1be669c39..e761359b56a9 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -18,6 +18,9 @@ struct flow_offload_entry {
struct rcu_head rcu_head;
};
+static DEFINE_MUTEX(flowtable_lock);
+static LIST_HEAD(flowtables);
+
static void
flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
struct nf_flow_route *route,
@@ -410,6 +413,10 @@ int nf_flow_table_init(struct nf_flowtable *flowtable)
queue_delayed_work(system_power_efficient_wq,
&flowtable->gc_work, HZ);
+ mutex_lock(&flowtable_lock);
+ list_add(&flowtable->list, &flowtables);
+ mutex_unlock(&flowtable_lock);
+
return 0;
}
EXPORT_SYMBOL_GPL(nf_flow_table_init);
@@ -425,20 +432,28 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
}
static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
- void *data)
+ struct net_device *dev)
{
- nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, data);
+ nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev);
flush_delayed_work(&flowtable->gc_work);
}
void nf_flow_table_cleanup(struct net *net, struct net_device *dev)
{
- nft_flow_table_iterate(net, nf_flow_table_iterate_cleanup, dev);
+ struct nf_flowtable *flowtable;
+
+ mutex_lock(&flowtable_lock);
+ list_for_each_entry(flowtable, &flowtables, list)
+ nf_flow_table_iterate_cleanup(flowtable, dev);
+ mutex_unlock(&flowtable_lock);
}
EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
void nf_flow_table_free(struct nf_flowtable *flow_table)
{
+ mutex_lock(&flowtable_lock);
+ list_del(&flow_table->list);
+ mutex_unlock(&flowtable_lock);
cancel_delayed_work_sync(&flow_table->gc_work);
nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
WARN_ON(!nf_flow_offload_gc_step(flow_table));
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 517bb93c00fb..16b67f54b3d2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5060,23 +5060,6 @@ static const struct nf_flowtable_type *nft_flowtable_type_get(u8 family)
return ERR_PTR(-ENOENT);
}
-void nft_flow_table_iterate(struct net *net,
- void (*iter)(struct nf_flowtable *flowtable, void *data),
- void *data)
-{
- struct nft_flowtable *flowtable;
- const struct nft_table *table;
-
- nfnl_lock(NFNL_SUBSYS_NFTABLES);
- list_for_each_entry(table, &net->nft.tables, list) {
- list_for_each_entry(flowtable, &table->flowtables, list) {
- iter(&flowtable->data, data);
- }
- }
- nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-}
-EXPORT_SYMBOL_GPL(nft_flow_table_iterate);
-
static void nft_unregister_flowtable_net_hooks(struct net *net,
struct nft_flowtable *flowtable)
{
--
2.11.0
^ permalink raw reply related
* [PATCH 19/51] netfilter: nf_flow_table: make flow_offload_dead inline
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
It is too trivial to keep as a separate exported function
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_flow_table.h | 5 ++++-
net/netfilter/nf_flow_table_core.c | 6 ------
2 files changed, 4 insertions(+), 7 deletions(-)
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index ab408adba688..5aa49524ebef 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -103,7 +103,10 @@ void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
int nf_flow_table_init(struct nf_flowtable *flow_table);
void nf_flow_table_free(struct nf_flowtable *flow_table);
-void flow_offload_dead(struct flow_offload *flow);
+static inline void flow_offload_dead(struct flow_offload *flow)
+{
+ flow->flags |= FLOW_OFFLOAD_DYING;
+}
int nf_flow_snat_port(const struct flow_offload *flow,
struct sk_buff *skb, unsigned int thoff,
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index e761359b56a9..0d38f20fd226 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -113,12 +113,6 @@ void flow_offload_free(struct flow_offload *flow)
}
EXPORT_SYMBOL_GPL(flow_offload_free);
-void flow_offload_dead(struct flow_offload *flow)
-{
- flow->flags |= FLOW_OFFLOAD_DYING;
-}
-EXPORT_SYMBOL_GPL(flow_offload_dead);
-
static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
{
const struct flow_offload_tuple *tuple = data;
--
2.11.0
^ permalink raw reply related
* [PATCH 16/51] netfilter: nf_flow_table: move init code to nf_flow_table_core.c
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Reduces duplication of .gc and .params in flowtable type definitions and
makes the API clearer
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_flow_table.h | 6 +-
net/ipv4/netfilter/nf_flow_table_ipv4.c | 3 +-
net/ipv6/netfilter/nf_flow_table_ipv6.c | 3 +-
net/netfilter/nf_flow_table_core.c | 102 +++++++++++++++++++-------------
net/netfilter/nf_flow_table_inet.c | 3 +-
net/netfilter/nf_tables_api.c | 22 +++----
6 files changed, 74 insertions(+), 65 deletions(-)
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 76ee5c81b752..f876e32a60b8 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -14,9 +14,8 @@ struct nf_flowtable;
struct nf_flowtable_type {
struct list_head list;
int family;
- void (*gc)(struct work_struct *work);
+ int (*init)(struct nf_flowtable *ft);
void (*free)(struct nf_flowtable *ft);
- const struct rhashtable_params *params;
nf_hookfn *hook;
struct module *owner;
};
@@ -100,9 +99,8 @@ int nf_flow_table_iterate(struct nf_flowtable *flow_table,
void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
+int nf_flow_table_init(struct nf_flowtable *flow_table);
void nf_flow_table_free(struct nf_flowtable *flow_table);
-void nf_flow_offload_work_gc(struct work_struct *work);
-extern const struct rhashtable_params nf_flow_offload_rhash_params;
void flow_offload_dead(struct flow_offload *flow);
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index b6e43ff0c7b7..e1e56d7123d2 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -7,8 +7,7 @@
static struct nf_flowtable_type flowtable_ipv4 = {
.family = NFPROTO_IPV4,
- .params = &nf_flow_offload_rhash_params,
- .gc = nf_flow_offload_work_gc,
+ .init = nf_flow_table_init,
.free = nf_flow_table_free,
.hook = nf_flow_offload_ip_hook,
.owner = THIS_MODULE,
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
index f1804ce8d561..c511d206bf9b 100644
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c
@@ -8,8 +8,7 @@
static struct nf_flowtable_type flowtable_ipv6 = {
.family = NFPROTO_IPV6,
- .params = &nf_flow_offload_rhash_params,
- .gc = nf_flow_offload_work_gc,
+ .init = nf_flow_table_init,
.free = nf_flow_table_free,
.hook = nf_flow_offload_ipv6_hook,
.owner = THIS_MODULE,
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 7403a0dfddf7..09d1be669c39 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -116,16 +116,50 @@ void flow_offload_dead(struct flow_offload *flow)
}
EXPORT_SYMBOL_GPL(flow_offload_dead);
+static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
+{
+ const struct flow_offload_tuple *tuple = data;
+
+ return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed);
+}
+
+static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed)
+{
+ const struct flow_offload_tuple_rhash *tuplehash = data;
+
+ return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed);
+}
+
+static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
+ const void *ptr)
+{
+ const struct flow_offload_tuple *tuple = arg->key;
+ const struct flow_offload_tuple_rhash *x = ptr;
+
+ if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir)))
+ return 1;
+
+ return 0;
+}
+
+static const struct rhashtable_params nf_flow_offload_rhash_params = {
+ .head_offset = offsetof(struct flow_offload_tuple_rhash, node),
+ .hashfn = flow_offload_hash,
+ .obj_hashfn = flow_offload_hash_obj,
+ .obj_cmpfn = flow_offload_hash_cmp,
+ .automatic_shrinking = true,
+};
+
int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
{
flow->timeout = (u32)jiffies;
rhashtable_insert_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
rhashtable_insert_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
return 0;
}
EXPORT_SYMBOL_GPL(flow_offload_add);
@@ -135,10 +169,10 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
{
rhashtable_remove_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
rhashtable_remove_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
flow_offload_free(flow);
}
@@ -148,7 +182,7 @@ flow_offload_lookup(struct nf_flowtable *flow_table,
struct flow_offload_tuple *tuple)
{
return rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
- *flow_table->type->params);
+ nf_flow_offload_rhash_params);
}
EXPORT_SYMBOL_GPL(flow_offload_lookup);
@@ -237,7 +271,7 @@ static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
return 1;
}
-void nf_flow_offload_work_gc(struct work_struct *work)
+static void nf_flow_offload_work_gc(struct work_struct *work)
{
struct nf_flowtable *flow_table;
@@ -245,42 +279,6 @@ void nf_flow_offload_work_gc(struct work_struct *work)
nf_flow_offload_gc_step(flow_table);
queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
}
-EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc);
-
-static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
-{
- const struct flow_offload_tuple *tuple = data;
-
- return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed);
-}
-
-static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed)
-{
- const struct flow_offload_tuple_rhash *tuplehash = data;
-
- return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed);
-}
-
-static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg,
- const void *ptr)
-{
- const struct flow_offload_tuple *tuple = arg->key;
- const struct flow_offload_tuple_rhash *x = ptr;
-
- if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir)))
- return 1;
-
- return 0;
-}
-
-const struct rhashtable_params nf_flow_offload_rhash_params = {
- .head_offset = offsetof(struct flow_offload_tuple_rhash, node),
- .hashfn = flow_offload_hash,
- .obj_hashfn = flow_offload_hash_obj,
- .obj_cmpfn = flow_offload_hash_cmp,
- .automatic_shrinking = true,
-};
-EXPORT_SYMBOL_GPL(nf_flow_offload_rhash_params);
static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
__be16 port, __be16 new_port)
@@ -398,6 +396,24 @@ int nf_flow_dnat_port(const struct flow_offload *flow,
}
EXPORT_SYMBOL_GPL(nf_flow_dnat_port);
+int nf_flow_table_init(struct nf_flowtable *flowtable)
+{
+ int err;
+
+ INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
+
+ err = rhashtable_init(&flowtable->rhashtable,
+ &nf_flow_offload_rhash_params);
+ if (err < 0)
+ return err;
+
+ queue_delayed_work(system_power_efficient_wq,
+ &flowtable->gc_work, HZ);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_init);
+
static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
{
struct net_device *dev = data;
@@ -423,8 +439,10 @@ EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
void nf_flow_table_free(struct nf_flowtable *flow_table)
{
+ cancel_delayed_work_sync(&flow_table->gc_work);
nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
WARN_ON(!nf_flow_offload_gc_step(flow_table));
+ rhashtable_destroy(&flow_table->rhashtable);
}
EXPORT_SYMBOL_GPL(nf_flow_table_free);
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 375a1881d93d..99771aa7e7ea 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -22,8 +22,7 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
static struct nf_flowtable_type flowtable_inet = {
.family = NFPROTO_INET,
- .params = &nf_flow_offload_rhash_params,
- .gc = nf_flow_offload_work_gc,
+ .init = nf_flow_table_init,
.free = nf_flow_table_free,
.hook = nf_flow_offload_inet_hook,
.owner = THIS_MODULE,
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9134cc429ad4..6cd9955916e5 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5150,14 +5150,14 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
}
flowtable->data.type = type;
- err = rhashtable_init(&flowtable->data.rhashtable, type->params);
+ err = type->init(&flowtable->data);
if (err < 0)
goto err3;
err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK],
flowtable);
if (err < 0)
- goto err3;
+ goto err4;
for (i = 0; i < flowtable->ops_len; i++) {
if (!flowtable->ops[i].dev)
@@ -5171,37 +5171,35 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
if (flowtable->ops[i].dev == ft->ops[k].dev &&
flowtable->ops[i].pf == ft->ops[k].pf) {
err = -EBUSY;
- goto err4;
+ goto err5;
}
}
}
err = nf_register_net_hook(net, &flowtable->ops[i]);
if (err < 0)
- goto err4;
+ goto err5;
}
err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
if (err < 0)
- goto err5;
-
- INIT_DEFERRABLE_WORK(&flowtable->data.gc_work, type->gc);
- queue_delayed_work(system_power_efficient_wq,
- &flowtable->data.gc_work, HZ);
+ goto err6;
list_add_tail_rcu(&flowtable->list, &table->flowtables);
table->use++;
return 0;
-err5:
+err6:
i = flowtable->ops_len;
-err4:
+err5:
for (k = i - 1; k >= 0; k--) {
kfree(flowtable->dev_name[k]);
nf_unregister_net_hook(net, &flowtable->ops[k]);
}
kfree(flowtable->ops);
+err4:
+ flowtable->data.type->free(&flowtable->data);
err3:
module_put(type->owner);
err2:
@@ -5485,11 +5483,9 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
{
- cancel_delayed_work_sync(&flowtable->data.gc_work);
kfree(flowtable->ops);
kfree(flowtable->name);
flowtable->data.type->free(&flowtable->data);
- rhashtable_destroy(&flowtable->data.rhashtable);
module_put(flowtable->data.type->owner);
}
--
2.11.0
^ permalink raw reply related
* [PATCH 17/51] netfilter: nf_flow_table: fix priv pointer for netdev hook
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
The offload ip hook expects a pointer to the flowtable, not to the
rhashtable. Since the rhashtable is the first member, this is safe for
the moment, but breaks as soon as the structure layout changes
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_tables_api.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 6cd9955916e5..517bb93c00fb 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5019,7 +5019,7 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
flowtable->ops[i].pf = NFPROTO_NETDEV;
flowtable->ops[i].hooknum = hooknum;
flowtable->ops[i].priority = priority;
- flowtable->ops[i].priv = &flowtable->data.rhashtable;
+ flowtable->ops[i].priv = &flowtable->data;
flowtable->ops[i].hook = flowtable->data.type->hook;
flowtable->ops[i].dev = dev_array[i];
flowtable->dev_name[i] = kstrdup(dev_array[i]->name,
--
2.11.0
^ permalink raw reply related
* [PATCH 14/51] netfilter: nf_flow_table: move ipv6 offload hook code to nf_flow_table
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Useful as preparation for adding iptables support for offload.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/ipv6/netfilter/nf_flow_table_ipv6.c | 232 --------------------------------
net/netfilter/nf_flow_table_ip.c | 215 +++++++++++++++++++++++++++++
2 files changed, 215 insertions(+), 232 deletions(-)
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
index 0e6328490142..f1804ce8d561 100644
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c
@@ -3,240 +3,8 @@
#include <linux/module.h>
#include <linux/netfilter.h>
#include <linux/rhashtable.h>
-#include <linux/ipv6.h>
-#include <linux/netdevice.h>
-#include <net/ipv6.h>
-#include <net/ip6_route.h>
-#include <net/neighbour.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_tables.h>
-/* For layer 4 checksum field offset. */
-#include <linux/tcp.h>
-#include <linux/udp.h>
-
-static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
- struct in6_addr *addr,
- struct in6_addr *new_addr)
-{
- struct tcphdr *tcph;
-
- if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
- skb_try_make_writable(skb, thoff + sizeof(*tcph)))
- return -1;
-
- tcph = (void *)(skb_network_header(skb) + thoff);
- inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32,
- new_addr->s6_addr32, true);
-
- return 0;
-}
-
-static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
- struct in6_addr *addr,
- struct in6_addr *new_addr)
-{
- struct udphdr *udph;
-
- if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
- skb_try_make_writable(skb, thoff + sizeof(*udph)))
- return -1;
-
- udph = (void *)(skb_network_header(skb) + thoff);
- if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
- inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32,
- new_addr->s6_addr32, true);
- if (!udph->check)
- udph->check = CSUM_MANGLED_0;
- }
-
- return 0;
-}
-
-static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h,
- unsigned int thoff, struct in6_addr *addr,
- struct in6_addr *new_addr)
-{
- switch (ip6h->nexthdr) {
- case IPPROTO_TCP:
- if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0)
- return NF_DROP;
- break;
- case IPPROTO_UDP:
- if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0)
- return NF_DROP;
- break;
- }
-
- return 0;
-}
-
-static int nf_flow_snat_ipv6(const struct flow_offload *flow,
- struct sk_buff *skb, struct ipv6hdr *ip6h,
- unsigned int thoff,
- enum flow_offload_tuple_dir dir)
-{
- struct in6_addr addr, new_addr;
-
- switch (dir) {
- case FLOW_OFFLOAD_DIR_ORIGINAL:
- addr = ip6h->saddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6;
- ip6h->saddr = new_addr;
- break;
- case FLOW_OFFLOAD_DIR_REPLY:
- addr = ip6h->daddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6;
- ip6h->daddr = new_addr;
- break;
- default:
- return -1;
- }
-
- return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
-}
-
-static int nf_flow_dnat_ipv6(const struct flow_offload *flow,
- struct sk_buff *skb, struct ipv6hdr *ip6h,
- unsigned int thoff,
- enum flow_offload_tuple_dir dir)
-{
- struct in6_addr addr, new_addr;
-
- switch (dir) {
- case FLOW_OFFLOAD_DIR_ORIGINAL:
- addr = ip6h->daddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6;
- ip6h->daddr = new_addr;
- break;
- case FLOW_OFFLOAD_DIR_REPLY:
- addr = ip6h->saddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6;
- ip6h->saddr = new_addr;
- break;
- default:
- return -1;
- }
-
- return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
-}
-
-static int nf_flow_nat_ipv6(const struct flow_offload *flow,
- struct sk_buff *skb,
- enum flow_offload_tuple_dir dir)
-{
- struct ipv6hdr *ip6h = ipv6_hdr(skb);
- unsigned int thoff = sizeof(*ip6h);
-
- if (flow->flags & FLOW_OFFLOAD_SNAT &&
- (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
- nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
- return -1;
- if (flow->flags & FLOW_OFFLOAD_DNAT &&
- (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
- nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
- return -1;
-
- return 0;
-}
-
-static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
- struct flow_offload_tuple *tuple)
-{
- struct flow_ports *ports;
- struct ipv6hdr *ip6h;
- unsigned int thoff;
-
- if (!pskb_may_pull(skb, sizeof(*ip6h)))
- return -1;
-
- ip6h = ipv6_hdr(skb);
-
- if (ip6h->nexthdr != IPPROTO_TCP &&
- ip6h->nexthdr != IPPROTO_UDP)
- return -1;
-
- thoff = sizeof(*ip6h);
- if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
- return -1;
-
- ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
-
- tuple->src_v6 = ip6h->saddr;
- tuple->dst_v6 = ip6h->daddr;
- tuple->src_port = ports->source;
- tuple->dst_port = ports->dest;
- tuple->l3proto = AF_INET6;
- tuple->l4proto = ip6h->nexthdr;
- tuple->iifidx = dev->ifindex;
-
- return 0;
-}
-
-/* Based on ip_exceeds_mtu(). */
-static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
-{
- if (skb->len <= mtu)
- return false;
-
- if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
- return false;
-
- return true;
-}
-
-unsigned int
-nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- struct flow_offload_tuple_rhash *tuplehash;
- struct nf_flowtable *flow_table = priv;
- struct flow_offload_tuple tuple = {};
- enum flow_offload_tuple_dir dir;
- struct flow_offload *flow;
- struct net_device *outdev;
- struct in6_addr *nexthop;
- struct ipv6hdr *ip6h;
- struct rt6_info *rt;
-
- if (skb->protocol != htons(ETH_P_IPV6))
- return NF_ACCEPT;
-
- if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0)
- return NF_ACCEPT;
-
- tuplehash = flow_offload_lookup(flow_table, &tuple);
- if (tuplehash == NULL)
- return NF_ACCEPT;
-
- outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
- if (!outdev)
- return NF_ACCEPT;
-
- dir = tuplehash->tuple.dir;
- flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
- rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
-
- if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
- return NF_ACCEPT;
-
- if (skb_try_make_writable(skb, sizeof(*ip6h)))
- return NF_DROP;
-
- if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
- nf_flow_nat_ipv6(flow, skb, dir) < 0)
- return NF_DROP;
-
- flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
- ip6h = ipv6_hdr(skb);
- ip6h->hop_limit--;
-
- skb->dev = outdev;
- nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
- neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
-
- return NF_STOLEN;
-}
-EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook);
static struct nf_flowtable_type flowtable_ipv6 = {
.family = NFPROTO_IPV6,
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 103263e0c7c2..dc570fb7641d 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -4,8 +4,11 @@
#include <linux/netfilter.h>
#include <linux/rhashtable.h>
#include <linux/ip.h>
+#include <linux/ipv6.h>
#include <linux/netdevice.h>
#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
#include <net/neighbour.h>
#include <net/netfilter/nf_flow_table.h>
/* For layer 4 checksum field offset. */
@@ -242,3 +245,215 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
return NF_STOLEN;
}
EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
+
+static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
+ struct in6_addr *addr,
+ struct in6_addr *new_addr)
+{
+ struct tcphdr *tcph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+ return -1;
+
+ tcph = (void *)(skb_network_header(skb) + thoff);
+ inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32,
+ new_addr->s6_addr32, true);
+
+ return 0;
+}
+
+static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
+ struct in6_addr *addr,
+ struct in6_addr *new_addr)
+{
+ struct udphdr *udph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*udph)))
+ return -1;
+
+ udph = (void *)(skb_network_header(skb) + thoff);
+ if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+ inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32,
+ new_addr->s6_addr32, true);
+ if (!udph->check)
+ udph->check = CSUM_MANGLED_0;
+ }
+
+ return 0;
+}
+
+static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h,
+ unsigned int thoff, struct in6_addr *addr,
+ struct in6_addr *new_addr)
+{
+ switch (ip6h->nexthdr) {
+ case IPPROTO_TCP:
+ if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0)
+ return NF_DROP;
+ break;
+ case IPPROTO_UDP:
+ if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0)
+ return NF_DROP;
+ break;
+ }
+
+ return 0;
+}
+
+static int nf_flow_snat_ipv6(const struct flow_offload *flow,
+ struct sk_buff *skb, struct ipv6hdr *ip6h,
+ unsigned int thoff,
+ enum flow_offload_tuple_dir dir)
+{
+ struct in6_addr addr, new_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = ip6h->saddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6;
+ ip6h->saddr = new_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = ip6h->daddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6;
+ ip6h->daddr = new_addr;
+ break;
+ default:
+ return -1;
+ }
+
+ return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
+}
+
+static int nf_flow_dnat_ipv6(const struct flow_offload *flow,
+ struct sk_buff *skb, struct ipv6hdr *ip6h,
+ unsigned int thoff,
+ enum flow_offload_tuple_dir dir)
+{
+ struct in6_addr addr, new_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = ip6h->daddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6;
+ ip6h->daddr = new_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = ip6h->saddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6;
+ ip6h->saddr = new_addr;
+ break;
+ default:
+ return -1;
+ }
+
+ return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
+}
+
+static int nf_flow_nat_ipv6(const struct flow_offload *flow,
+ struct sk_buff *skb,
+ enum flow_offload_tuple_dir dir)
+{
+ struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ unsigned int thoff = sizeof(*ip6h);
+
+ if (flow->flags & FLOW_OFFLOAD_SNAT &&
+ (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
+ nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
+ return -1;
+ if (flow->flags & FLOW_OFFLOAD_DNAT &&
+ (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
+ nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
+ return -1;
+
+ return 0;
+}
+
+static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
+ struct flow_offload_tuple *tuple)
+{
+ struct flow_ports *ports;
+ struct ipv6hdr *ip6h;
+ unsigned int thoff;
+
+ if (!pskb_may_pull(skb, sizeof(*ip6h)))
+ return -1;
+
+ ip6h = ipv6_hdr(skb);
+
+ if (ip6h->nexthdr != IPPROTO_TCP &&
+ ip6h->nexthdr != IPPROTO_UDP)
+ return -1;
+
+ thoff = sizeof(*ip6h);
+ if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+ return -1;
+
+ ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+
+ tuple->src_v6 = ip6h->saddr;
+ tuple->dst_v6 = ip6h->daddr;
+ tuple->src_port = ports->source;
+ tuple->dst_port = ports->dest;
+ tuple->l3proto = AF_INET6;
+ tuple->l4proto = ip6h->nexthdr;
+ tuple->iifidx = dev->ifindex;
+
+ return 0;
+}
+
+unsigned int
+nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct nf_flowtable *flow_table = priv;
+ struct flow_offload_tuple tuple = {};
+ enum flow_offload_tuple_dir dir;
+ struct flow_offload *flow;
+ struct net_device *outdev;
+ struct in6_addr *nexthop;
+ struct ipv6hdr *ip6h;
+ struct rt6_info *rt;
+
+ if (skb->protocol != htons(ETH_P_IPV6))
+ return NF_ACCEPT;
+
+ if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0)
+ return NF_ACCEPT;
+
+ tuplehash = flow_offload_lookup(flow_table, &tuple);
+ if (tuplehash == NULL)
+ return NF_ACCEPT;
+
+ outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
+ if (!outdev)
+ return NF_ACCEPT;
+
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+ rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
+
+ if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
+ return NF_ACCEPT;
+
+ if (skb_try_make_writable(skb, sizeof(*ip6h)))
+ return NF_DROP;
+
+ if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
+ nf_flow_nat_ipv6(flow, skb, dir) < 0)
+ return NF_DROP;
+
+ flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+ ip6h = ipv6_hdr(skb);
+ ip6h->hop_limit--;
+
+ skb->dev = outdev;
+ nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
+ neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
+
+ return NF_STOLEN;
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook);
--
2.11.0
^ permalink raw reply related
* [PATCH 15/51] netfilter: nf_flow_table: relax mixed ipv4/ipv6 flowtable dependencies
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Since the offload hook code was moved, this table no longer depends on
the IPv4 and IPv6 flowtable modules
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/Kconfig | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 704b3832dbad..d20664b02ae4 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -666,8 +666,7 @@ endif # NF_TABLES
config NF_FLOW_TABLE_INET
tristate "Netfilter flow table mixed IPv4/IPv6 module"
- depends on NF_FLOW_TABLE_IPV4
- depends on NF_FLOW_TABLE_IPV6
+ depends on NF_FLOW_TABLE
help
This option adds the flow table mixed IPv4/IPv6 support.
--
2.11.0
^ permalink raw reply related
* [PATCH 13/51] netfilter: nf_flow_table: move ip header check out of nf_flow_exceeds_mtu
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Allows the function to be shared with the IPv6 hook code
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table_ip.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 034fda963392..103263e0c7c2 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -182,9 +182,6 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
if (skb->len <= mtu)
return false;
- if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
- return false;
-
if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
return false;
@@ -223,7 +220,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
- if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
+ if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) &&
+ (ip_hdr(skb)->frag_off & htons(IP_DF)) != 0)
return NF_ACCEPT;
if (skb_try_make_writable(skb, sizeof(*iph)))
--
2.11.0
^ permalink raw reply related
* [PATCH 12/51] netfilter: nf_flow_table: move ipv4 offload hook code to nf_flow_table
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Allows some minor code sharing with the ipv6 hook code and is also
useful as preparation for adding iptables support for offload
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/ipv4/netfilter/nf_flow_table_ipv4.c | 241 -------------------------------
net/netfilter/Makefile | 2 +-
net/netfilter/nf_flow_table_ip.c | 246 ++++++++++++++++++++++++++++++++
3 files changed, 247 insertions(+), 242 deletions(-)
create mode 100644 net/netfilter/nf_flow_table_ip.c
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index 461b1815e633..b6e43ff0c7b7 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -2,249 +2,8 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netfilter.h>
-#include <linux/rhashtable.h>
-#include <linux/ip.h>
-#include <linux/netdevice.h>
-#include <net/ip.h>
-#include <net/neighbour.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_tables.h>
-/* For layer 4 checksum field offset. */
-#include <linux/tcp.h>
-#include <linux/udp.h>
-
-static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
- __be32 addr, __be32 new_addr)
-{
- struct tcphdr *tcph;
-
- if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
- skb_try_make_writable(skb, thoff + sizeof(*tcph)))
- return -1;
-
- tcph = (void *)(skb_network_header(skb) + thoff);
- inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
-
- return 0;
-}
-
-static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
- __be32 addr, __be32 new_addr)
-{
- struct udphdr *udph;
-
- if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
- skb_try_make_writable(skb, thoff + sizeof(*udph)))
- return -1;
-
- udph = (void *)(skb_network_header(skb) + thoff);
- if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
- inet_proto_csum_replace4(&udph->check, skb, addr,
- new_addr, true);
- if (!udph->check)
- udph->check = CSUM_MANGLED_0;
- }
-
- return 0;
-}
-
-static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
- unsigned int thoff, __be32 addr,
- __be32 new_addr)
-{
- switch (iph->protocol) {
- case IPPROTO_TCP:
- if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
- return NF_DROP;
- break;
- case IPPROTO_UDP:
- if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
- return NF_DROP;
- break;
- }
-
- return 0;
-}
-
-static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
- struct iphdr *iph, unsigned int thoff,
- enum flow_offload_tuple_dir dir)
-{
- __be32 addr, new_addr;
-
- switch (dir) {
- case FLOW_OFFLOAD_DIR_ORIGINAL:
- addr = iph->saddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
- iph->saddr = new_addr;
- break;
- case FLOW_OFFLOAD_DIR_REPLY:
- addr = iph->daddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
- iph->daddr = new_addr;
- break;
- default:
- return -1;
- }
- csum_replace4(&iph->check, addr, new_addr);
-
- return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
-}
-
-static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
- struct iphdr *iph, unsigned int thoff,
- enum flow_offload_tuple_dir dir)
-{
- __be32 addr, new_addr;
-
- switch (dir) {
- case FLOW_OFFLOAD_DIR_ORIGINAL:
- addr = iph->daddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
- iph->daddr = new_addr;
- break;
- case FLOW_OFFLOAD_DIR_REPLY:
- addr = iph->saddr;
- new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
- iph->saddr = new_addr;
- break;
- default:
- return -1;
- }
- csum_replace4(&iph->check, addr, new_addr);
-
- return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
-}
-
-static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
- enum flow_offload_tuple_dir dir)
-{
- struct iphdr *iph = ip_hdr(skb);
- unsigned int thoff = iph->ihl * 4;
-
- if (flow->flags & FLOW_OFFLOAD_SNAT &&
- (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
- nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
- return -1;
- if (flow->flags & FLOW_OFFLOAD_DNAT &&
- (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
- nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
- return -1;
-
- return 0;
-}
-
-static bool ip_has_options(unsigned int thoff)
-{
- return thoff != sizeof(struct iphdr);
-}
-
-static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
- struct flow_offload_tuple *tuple)
-{
- struct flow_ports *ports;
- unsigned int thoff;
- struct iphdr *iph;
-
- if (!pskb_may_pull(skb, sizeof(*iph)))
- return -1;
-
- iph = ip_hdr(skb);
- thoff = iph->ihl * 4;
-
- if (ip_is_fragment(iph) ||
- unlikely(ip_has_options(thoff)))
- return -1;
-
- if (iph->protocol != IPPROTO_TCP &&
- iph->protocol != IPPROTO_UDP)
- return -1;
-
- thoff = iph->ihl * 4;
- if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
- return -1;
-
- ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
-
- tuple->src_v4.s_addr = iph->saddr;
- tuple->dst_v4.s_addr = iph->daddr;
- tuple->src_port = ports->source;
- tuple->dst_port = ports->dest;
- tuple->l3proto = AF_INET;
- tuple->l4proto = iph->protocol;
- tuple->iifidx = dev->ifindex;
-
- return 0;
-}
-
-/* Based on ip_exceeds_mtu(). */
-static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
-{
- if (skb->len <= mtu)
- return false;
-
- if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
- return false;
-
- if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
- return false;
-
- return true;
-}
-
-unsigned int
-nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- struct flow_offload_tuple_rhash *tuplehash;
- struct nf_flowtable *flow_table = priv;
- struct flow_offload_tuple tuple = {};
- enum flow_offload_tuple_dir dir;
- struct flow_offload *flow;
- struct net_device *outdev;
- const struct rtable *rt;
- struct iphdr *iph;
- __be32 nexthop;
-
- if (skb->protocol != htons(ETH_P_IP))
- return NF_ACCEPT;
-
- if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
- return NF_ACCEPT;
-
- tuplehash = flow_offload_lookup(flow_table, &tuple);
- if (tuplehash == NULL)
- return NF_ACCEPT;
-
- outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
- if (!outdev)
- return NF_ACCEPT;
-
- dir = tuplehash->tuple.dir;
- flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
- rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
-
- if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
- return NF_ACCEPT;
-
- if (skb_try_make_writable(skb, sizeof(*iph)))
- return NF_DROP;
-
- if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
- nf_flow_nat_ip(flow, skb, dir) < 0)
- return NF_DROP;
-
- flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
- iph = ip_hdr(skb);
- ip_decrease_ttl(iph);
-
- skb->dev = outdev;
- nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
- neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
-
- return NF_STOLEN;
-}
-EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
static struct nf_flowtable_type flowtable_ipv4 = {
.family = NFPROTO_IPV4,
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 700c5d51e405..3103ed1efe17 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -111,7 +111,7 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o
# flow table infrastructure
obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o
-nf_flow_table-objs := nf_flow_table_core.o
+nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o
obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
new file mode 100644
index 000000000000..034fda963392
--- /dev/null
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -0,0 +1,246 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rhashtable.h>
+#include <linux/ip.h>
+#include <linux/netdevice.h>
+#include <net/ip.h>
+#include <net/neighbour.h>
+#include <net/netfilter/nf_flow_table.h>
+/* For layer 4 checksum field offset. */
+#include <linux/tcp.h>
+#include <linux/udp.h>
+
+static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
+ __be32 addr, __be32 new_addr)
+{
+ struct tcphdr *tcph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+ return -1;
+
+ tcph = (void *)(skb_network_header(skb) + thoff);
+ inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
+
+ return 0;
+}
+
+static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
+ __be32 addr, __be32 new_addr)
+{
+ struct udphdr *udph;
+
+ if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
+ skb_try_make_writable(skb, thoff + sizeof(*udph)))
+ return -1;
+
+ udph = (void *)(skb_network_header(skb) + thoff);
+ if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+ inet_proto_csum_replace4(&udph->check, skb, addr,
+ new_addr, true);
+ if (!udph->check)
+ udph->check = CSUM_MANGLED_0;
+ }
+
+ return 0;
+}
+
+static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
+ unsigned int thoff, __be32 addr,
+ __be32 new_addr)
+{
+ switch (iph->protocol) {
+ case IPPROTO_TCP:
+ if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
+ return NF_DROP;
+ break;
+ case IPPROTO_UDP:
+ if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
+ return NF_DROP;
+ break;
+ }
+
+ return 0;
+}
+
+static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+ struct iphdr *iph, unsigned int thoff,
+ enum flow_offload_tuple_dir dir)
+{
+ __be32 addr, new_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = iph->saddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
+ iph->saddr = new_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = iph->daddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
+ iph->daddr = new_addr;
+ break;
+ default:
+ return -1;
+ }
+ csum_replace4(&iph->check, addr, new_addr);
+
+ return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+}
+
+static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+ struct iphdr *iph, unsigned int thoff,
+ enum flow_offload_tuple_dir dir)
+{
+ __be32 addr, new_addr;
+
+ switch (dir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ addr = iph->daddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
+ iph->daddr = new_addr;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ addr = iph->saddr;
+ new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
+ iph->saddr = new_addr;
+ break;
+ default:
+ return -1;
+ }
+ csum_replace4(&iph->check, addr, new_addr);
+
+ return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
+}
+
+static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
+ enum flow_offload_tuple_dir dir)
+{
+ struct iphdr *iph = ip_hdr(skb);
+ unsigned int thoff = iph->ihl * 4;
+
+ if (flow->flags & FLOW_OFFLOAD_SNAT &&
+ (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
+ nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
+ return -1;
+ if (flow->flags & FLOW_OFFLOAD_DNAT &&
+ (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
+ nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
+ return -1;
+
+ return 0;
+}
+
+static bool ip_has_options(unsigned int thoff)
+{
+ return thoff != sizeof(struct iphdr);
+}
+
+static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
+ struct flow_offload_tuple *tuple)
+{
+ struct flow_ports *ports;
+ unsigned int thoff;
+ struct iphdr *iph;
+
+ if (!pskb_may_pull(skb, sizeof(*iph)))
+ return -1;
+
+ iph = ip_hdr(skb);
+ thoff = iph->ihl * 4;
+
+ if (ip_is_fragment(iph) ||
+ unlikely(ip_has_options(thoff)))
+ return -1;
+
+ if (iph->protocol != IPPROTO_TCP &&
+ iph->protocol != IPPROTO_UDP)
+ return -1;
+
+ thoff = iph->ihl * 4;
+ if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+ return -1;
+
+ ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+
+ tuple->src_v4.s_addr = iph->saddr;
+ tuple->dst_v4.s_addr = iph->daddr;
+ tuple->src_port = ports->source;
+ tuple->dst_port = ports->dest;
+ tuple->l3proto = AF_INET;
+ tuple->l4proto = iph->protocol;
+ tuple->iifidx = dev->ifindex;
+
+ return 0;
+}
+
+/* Based on ip_exceeds_mtu(). */
+static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu)
+ return false;
+
+ if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
+ return false;
+
+ return true;
+}
+
+unsigned int
+nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct nf_flowtable *flow_table = priv;
+ struct flow_offload_tuple tuple = {};
+ enum flow_offload_tuple_dir dir;
+ struct flow_offload *flow;
+ struct net_device *outdev;
+ const struct rtable *rt;
+ struct iphdr *iph;
+ __be32 nexthop;
+
+ if (skb->protocol != htons(ETH_P_IP))
+ return NF_ACCEPT;
+
+ if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
+ return NF_ACCEPT;
+
+ tuplehash = flow_offload_lookup(flow_table, &tuple);
+ if (tuplehash == NULL)
+ return NF_ACCEPT;
+
+ outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
+ if (!outdev)
+ return NF_ACCEPT;
+
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+ rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
+
+ if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
+ return NF_ACCEPT;
+
+ if (skb_try_make_writable(skb, sizeof(*iph)))
+ return NF_DROP;
+
+ if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
+ nf_flow_nat_ip(flow, skb, dir) < 0)
+ return NF_DROP;
+
+ flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+ iph = ip_hdr(skb);
+ ip_decrease_ttl(iph);
+
+ skb->dev = outdev;
+ nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
+ neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
+
+ return NF_STOLEN;
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
--
2.11.0
^ permalink raw reply related
* [PATCH 11/51] netfilter: nf_flow_table: rename nf_flow_table.c to nf_flow_table_core.c
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Preparation for adding more code to the same module
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/Makefile | 2 ++
net/netfilter/{nf_flow_table.c => nf_flow_table_core.c} | 0
2 files changed, 2 insertions(+)
rename net/netfilter/{nf_flow_table.c => nf_flow_table_core.c} (100%)
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index fd32bd2c9521..700c5d51e405 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -111,6 +111,8 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o
# flow table infrastructure
obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o
+nf_flow_table-objs := nf_flow_table_core.o
+
obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o
# generic X tables
diff --git a/net/netfilter/nf_flow_table.c b/net/netfilter/nf_flow_table_core.c
similarity index 100%
rename from net/netfilter/nf_flow_table.c
rename to net/netfilter/nf_flow_table_core.c
--
2.11.0
^ permalink raw reply related
* [PATCH 10/51] netfilter: nf_flow_table: cache mtu in struct flow_offload_tuple
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Reduces the number of cache lines touched in the offload forwarding
path. This is safe because PMTU limits are bypassed for the forwarding
path (see commit f87c10a8aa1e for more details).
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_flow_table.h | 2 ++
net/ipv4/netfilter/nf_flow_table_ipv4.c | 17 +++--------------
net/ipv6/netfilter/nf_flow_table_ipv6.c | 17 +++--------------
net/netfilter/nf_flow_table.c | 8 ++++++--
4 files changed, 14 insertions(+), 30 deletions(-)
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 09ba67598991..76ee5c81b752 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -55,6 +55,8 @@ struct flow_offload_tuple {
int oifidx;
+ u16 mtu;
+
struct dst_entry *dst_cache;
};
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index 0cd46bffa469..461b1815e633 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -178,7 +178,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
}
/* Based on ip_exceeds_mtu(). */
-static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
{
if (skb->len <= mtu)
return false;
@@ -192,17 +192,6 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
return true;
}
-static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rtable *rt)
-{
- u32 mtu;
-
- mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
- if (__nf_flow_exceeds_mtu(skb, mtu))
- return true;
-
- return false;
-}
-
unsigned int
nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
@@ -233,9 +222,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-
rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
- if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
+
+ if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
return NF_ACCEPT;
if (skb_try_make_writable(skb, sizeof(*iph)))
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
index 207cb35569b1..0e6328490142 100644
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c
@@ -173,7 +173,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
}
/* Based on ip_exceeds_mtu(). */
-static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
{
if (skb->len <= mtu)
return false;
@@ -184,17 +184,6 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
return true;
}
-static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rt6_info *rt)
-{
- u32 mtu;
-
- mtu = ip6_dst_mtu_forward(&rt->dst);
- if (__nf_flow_exceeds_mtu(skb, mtu))
- return true;
-
- return false;
-}
-
unsigned int
nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
@@ -225,9 +214,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-
rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
- if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
+
+ if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
return NF_ACCEPT;
if (skb_try_make_writable(skb, sizeof(*ip6h)))
diff --git a/net/netfilter/nf_flow_table.c b/net/netfilter/nf_flow_table.c
index db0673a40b97..7403a0dfddf7 100644
--- a/net/netfilter/nf_flow_table.c
+++ b/net/netfilter/nf_flow_table.c
@@ -4,6 +4,8 @@
#include <linux/netfilter.h>
#include <linux/rhashtable.h>
#include <linux/netdevice.h>
+#include <net/ip.h>
+#include <net/ip6_route.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_conntrack.h>
@@ -23,6 +25,7 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
{
struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple;
struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple;
+ struct dst_entry *dst = route->tuple[dir].dst;
ft->dir = dir;
@@ -30,10 +33,12 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
case NFPROTO_IPV4:
ft->src_v4 = ctt->src.u3.in;
ft->dst_v4 = ctt->dst.u3.in;
+ ft->mtu = ip_dst_mtu_maybe_forward(dst, true);
break;
case NFPROTO_IPV6:
ft->src_v6 = ctt->src.u3.in6;
ft->dst_v6 = ctt->dst.u3.in6;
+ ft->mtu = ip6_dst_mtu_forward(dst);
break;
}
@@ -44,8 +49,7 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
ft->iifidx = route->tuple[dir].ifindex;
ft->oifidx = route->tuple[!dir].ifindex;
-
- ft->dst_cache = route->tuple[dir].dst;
+ ft->dst_cache = dst;
}
struct flow_offload *
--
2.11.0
^ permalink raw reply related
* [PATCH 08/51] netfilter: nf_flow_table: clean up flow_offload_alloc
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Reduce code duplication and make it much easier to read
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_flow_table.c | 93 ++++++++++++++++---------------------------
1 file changed, 34 insertions(+), 59 deletions(-)
diff --git a/net/netfilter/nf_flow_table.c b/net/netfilter/nf_flow_table.c
index ec410cae9307..db0673a40b97 100644
--- a/net/netfilter/nf_flow_table.c
+++ b/net/netfilter/nf_flow_table.c
@@ -16,6 +16,38 @@ struct flow_offload_entry {
struct rcu_head rcu_head;
};
+static void
+flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
+ struct nf_flow_route *route,
+ enum flow_offload_tuple_dir dir)
+{
+ struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple;
+ struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple;
+
+ ft->dir = dir;
+
+ switch (ctt->src.l3num) {
+ case NFPROTO_IPV4:
+ ft->src_v4 = ctt->src.u3.in;
+ ft->dst_v4 = ctt->dst.u3.in;
+ break;
+ case NFPROTO_IPV6:
+ ft->src_v6 = ctt->src.u3.in6;
+ ft->dst_v6 = ctt->dst.u3.in6;
+ break;
+ }
+
+ ft->l3proto = ctt->src.l3num;
+ ft->l4proto = ctt->dst.protonum;
+ ft->src_port = ctt->src.u.tcp.port;
+ ft->dst_port = ctt->dst.u.tcp.port;
+
+ ft->iifidx = route->tuple[dir].ifindex;
+ ft->oifidx = route->tuple[!dir].ifindex;
+
+ ft->dst_cache = route->tuple[dir].dst;
+}
+
struct flow_offload *
flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
{
@@ -40,65 +72,8 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
entry->ct = ct;
- switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num) {
- case NFPROTO_IPV4:
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4 =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4 =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4 =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4 =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in;
- break;
- case NFPROTO_IPV6:
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6 =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6 =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6 =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in6;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6 =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in6;
- break;
- }
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l3proto =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l3proto =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l4proto =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache =
- route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache =
- route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst;
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port =
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.tcp.port;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port =
- ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port;
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dir =
- FLOW_OFFLOAD_DIR_ORIGINAL;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dir =
- FLOW_OFFLOAD_DIR_REPLY;
-
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx =
- route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
- flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.oifidx =
- route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx =
- route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
- flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.oifidx =
- route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
+ flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_ORIGINAL);
+ flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_REPLY);
if (ct->status & IPS_SRC_NAT)
flow->flags |= FLOW_OFFLOAD_SNAT;
--
2.11.0
^ permalink raw reply related
* [PATCH 09/51] ipv6: make ip6_dst_mtu_forward inline
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Just like ip_dst_mtu_maybe_forward(), to avoid a dependency with ipv6.ko.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/ip6_route.h | 21 +++++++++++++++++++++
include/net/ipv6.h | 2 --
net/ipv6/ip6_output.c | 22 ----------------------
3 files changed, 21 insertions(+), 24 deletions(-)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index d5fb1e4ae7ac..376928c26d2d 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -279,6 +279,27 @@ static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *
!lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate);
}
+static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+{
+ struct inet6_dev *idev;
+ unsigned int mtu;
+
+ if (dst_metric_locked(dst, RTAX_MTU)) {
+ mtu = dst_metric_raw(dst, RTAX_MTU);
+ if (mtu)
+ return mtu;
+ }
+
+ mtu = IPV6_MIN_MTU;
+ rcu_read_lock();
+ idev = __in6_dev_get(dst->dev);
+ if (idev)
+ mtu = idev->cnf.mtu6;
+ rcu_read_unlock();
+
+ return mtu;
+}
+
struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
struct net_device *dev, struct sk_buff *skb,
const void *daddr);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 68b167d98879..765441867cfa 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -958,8 +958,6 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
&inet6_sk(sk)->cork);
}
-unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst);
-
int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
struct flowi6 *fl6);
struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3db47986ef38..cec49e137dbb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -383,28 +383,6 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
return dst_output(net, sk, skb);
}
-unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
-{
- unsigned int mtu;
- struct inet6_dev *idev;
-
- if (dst_metric_locked(dst, RTAX_MTU)) {
- mtu = dst_metric_raw(dst, RTAX_MTU);
- if (mtu)
- return mtu;
- }
-
- mtu = IPV6_MIN_MTU;
- rcu_read_lock();
- idev = __in6_dev_get(dst->dev);
- if (idev)
- mtu = idev->cnf.mtu6;
- rcu_read_unlock();
-
- return mtu;
-}
-EXPORT_SYMBOL_GPL(ip6_dst_mtu_forward);
-
static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
{
if (skb->len <= mtu)
--
2.11.0
^ permalink raw reply related
* [PATCH 07/51] netfilter: nf_flow_table: use IP_CT_DIR_* values for FLOW_OFFLOAD_DIR_*
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Felix Fietkau <nbd@nbd.name>
Simplifies further code cleanups
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_flow_table.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 833752dd0c58..09ba67598991 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -6,6 +6,7 @@
#include <linux/netdevice.h>
#include <linux/rhashtable.h>
#include <linux/rcupdate.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
#include <net/dst.h>
struct nf_flowtable;
@@ -27,11 +28,10 @@ struct nf_flowtable {
};
enum flow_offload_tuple_dir {
- FLOW_OFFLOAD_DIR_ORIGINAL,
- FLOW_OFFLOAD_DIR_REPLY,
- __FLOW_OFFLOAD_DIR_MAX = FLOW_OFFLOAD_DIR_REPLY,
+ FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL,
+ FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY,
+ FLOW_OFFLOAD_DIR_MAX = IP_CT_DIR_MAX
};
-#define FLOW_OFFLOAD_DIR_MAX (__FLOW_OFFLOAD_DIR_MAX + 1)
struct flow_offload_tuple {
union {
--
2.11.0
^ permalink raw reply related
* [PATCH 06/51] netfilter: xt_NFLOG: use nf_log_packet instead of nfulnl_log_packet.
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Taehee Yoo <ap420073@gmail.com>
The nfulnl_log_packet() is added to make sure that the NFLOG target
works as only user-space logger. but now, nf_log_packet() can find proper
log function using NF_LOG_TYPE_ULOG and NF_LOG_TYPE_LOG.
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nfnetlink_log.h | 17 -----------------
net/netfilter/nfnetlink_log.c | 8 +++-----
net/netfilter/xt_NFLOG.c | 15 +++++++++++----
3 files changed, 14 insertions(+), 26 deletions(-)
diff --git a/include/net/netfilter/nfnetlink_log.h b/include/net/netfilter/nfnetlink_log.h
index 612cfb63ac68..ea32a7d3cf1b 100644
--- a/include/net/netfilter/nfnetlink_log.h
+++ b/include/net/netfilter/nfnetlink_log.h
@@ -1,18 +1 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _KER_NFNETLINK_LOG_H
-#define _KER_NFNETLINK_LOG_H
-
-void
-nfulnl_log_packet(struct net *net,
- u_int8_t pf,
- unsigned int hooknum,
- const struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- const struct nf_loginfo *li_user,
- const char *prefix);
-
-#define NFULNL_COPY_DISABLED 0xff
-
-#endif /* _KER_NFNETLINK_LOG_H */
-
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 7b46aa4c478d..e5cc4d9b9ce7 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -37,7 +37,6 @@
#include <net/sock.h>
#include <net/netfilter/nf_log.h>
#include <net/netns/generic.h>
-#include <net/netfilter/nfnetlink_log.h>
#include <linux/atomic.h>
#include <linux/refcount.h>
@@ -47,6 +46,7 @@
#include "../bridge/br_private.h"
#endif
+#define NFULNL_COPY_DISABLED 0xff
#define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE
#define NFULNL_TIMEOUT_DEFAULT 100 /* every second */
#define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */
@@ -618,7 +618,7 @@ static const struct nf_loginfo default_loginfo = {
};
/* log handler for internal netfilter logging api */
-void
+static void
nfulnl_log_packet(struct net *net,
u_int8_t pf,
unsigned int hooknum,
@@ -633,7 +633,7 @@ nfulnl_log_packet(struct net *net,
struct nfulnl_instance *inst;
const struct nf_loginfo *li;
unsigned int qthreshold;
- unsigned int plen;
+ unsigned int plen = 0;
struct nfnl_log_net *log = nfnl_log_pernet(net);
const struct nfnl_ct_hook *nfnl_ct = NULL;
struct nf_conn *ct = NULL;
@@ -648,7 +648,6 @@ nfulnl_log_packet(struct net *net,
if (!inst)
return;
- plen = 0;
if (prefix)
plen = strlen(prefix) + 1;
@@ -760,7 +759,6 @@ nfulnl_log_packet(struct net *net,
/* FIXME: statistics */
goto unlock_and_release;
}
-EXPORT_SYMBOL_GPL(nfulnl_log_packet);
static int
nfulnl_rcv_nl_event(struct notifier_block *this,
diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c
index c7f8958cea4a..1ed0cac585c4 100644
--- a/net/netfilter/xt_NFLOG.c
+++ b/net/netfilter/xt_NFLOG.c
@@ -13,7 +13,6 @@
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_NFLOG.h>
#include <net/netfilter/nf_log.h>
-#include <net/netfilter/nfnetlink_log.h>
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_DESCRIPTION("Xtables: packet logging to netlink using NFLOG");
@@ -37,8 +36,9 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
if (info->flags & XT_NFLOG_F_COPY_LEN)
li.u.ulog.flags |= NF_LOG_F_COPY_LEN;
- nfulnl_log_packet(net, xt_family(par), xt_hooknum(par), skb,
- xt_in(par), xt_out(par), &li, info->prefix);
+ nf_log_packet(net, xt_family(par), xt_hooknum(par), skb, xt_in(par),
+ xt_out(par), &li, "%s", info->prefix);
+
return XT_CONTINUE;
}
@@ -50,7 +50,13 @@ static int nflog_tg_check(const struct xt_tgchk_param *par)
return -EINVAL;
if (info->prefix[sizeof(info->prefix) - 1] != '\0')
return -EINVAL;
- return 0;
+
+ return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+}
+
+static void nflog_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ nf_logger_put(par->family, NF_LOG_TYPE_ULOG);
}
static struct xt_target nflog_tg_reg __read_mostly = {
@@ -58,6 +64,7 @@ static struct xt_target nflog_tg_reg __read_mostly = {
.revision = 0,
.family = NFPROTO_UNSPEC,
.checkentry = nflog_tg_check,
+ .destroy = nflog_tg_destroy,
.target = nflog_tg,
.targetsize = sizeof(struct xt_nflog_info),
.me = THIS_MODULE,
--
2.11.0
^ permalink raw reply related
* [PATCH 05/51] ipvs: fix multiplicative hashing in sh/dh/lblc/lblcr algorithms
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Vincent Bernat <vincent@bernat.im>
The sh/dh/lblc/lblcr algorithms are using Knuth's multiplicative
hashing incorrectly. Replace its use by the hash_32() macro, which
correctly implements this algorithm. It doesn't use the same constant,
but it shouldn't matter.
Signed-off-by: Vincent Bernat <vincent@bernat.im>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_dh.c | 3 ++-
net/netfilter/ipvs/ip_vs_lblc.c | 3 ++-
net/netfilter/ipvs/ip_vs_lblcr.c | 3 ++-
net/netfilter/ipvs/ip_vs_sh.c | 3 ++-
4 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index 75f798f8e83b..07459e71d907 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -43,6 +43,7 @@
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
+#include <linux/hash.h>
#include <net/ip_vs.h>
@@ -81,7 +82,7 @@ static inline unsigned int ip_vs_dh_hashkey(int af, const union nf_inet_addr *ad
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (ntohl(addr_fold)*2654435761UL) & IP_VS_DH_TAB_MASK;
+ return hash_32(ntohl(addr_fold), IP_VS_DH_TAB_BITS);
}
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 3057e453bf31..08147fc6400c 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -48,6 +48,7 @@
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/jiffies.h>
+#include <linux/hash.h>
/* for sysctl */
#include <linux/fs.h>
@@ -160,7 +161,7 @@ ip_vs_lblc_hashkey(int af, const union nf_inet_addr *addr)
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLC_TAB_MASK;
+ return hash_32(ntohl(addr_fold), IP_VS_LBLC_TAB_BITS);
}
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 92adc04557ed..9b6a6c9e9cfa 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -47,6 +47,7 @@
#include <linux/jiffies.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/hash.h>
/* for sysctl */
#include <linux/fs.h>
@@ -323,7 +324,7 @@ ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr)
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLCR_TAB_MASK;
+ return hash_32(ntohl(addr_fold), IP_VS_LBLCR_TAB_BITS);
}
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 16aaac6eedc9..1e01c782583a 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -96,7 +96,8 @@ ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr,
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (offset + (ntohs(port) + ntohl(addr_fold))*2654435761UL) &
+ return (offset + hash_32(ntohs(port) + ntohl(addr_fold),
+ IP_VS_SH_TAB_BITS)) &
IP_VS_SH_TAB_MASK;
}
--
2.11.0
^ permalink raw reply related
* [PATCH 04/51] netfilter: ipvs: Add configurations of Maglev hashing
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=y, Size: 3306 bytes --]
From: Inju Song <inju.song@navercorp.com>
To build the maglev hashing scheduler, add some configuration
to Kconfig and Makefile.
- The compile configurations of MH are added to the Kconfig.
- The MH build rule is added to the Makefile.
Signed-off-by: Inju Song <inju.song@navercorp.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/Kconfig | 37 +++++++++++++++++++++++++++++++++++++
net/netfilter/ipvs/Makefile | 1 +
2 files changed, 38 insertions(+)
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index b32fb0dbe237..05dc1b77e466 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -225,6 +225,25 @@ config IP_VS_SH
If you want to compile it in kernel, say Y. To compile it as a
module, choose M here. If unsure, say N.
+config IP_VS_MH
+ tristate "maglev hashing scheduling"
+ ---help---
+ The maglev consistent hashing scheduling algorithm provides the
+ Google's Maglev hashing algorithm as a IPVS scheduler. It assigns
+ network connections to the servers through looking up a statically
+ assigned special hash table called the lookup table. Maglev hashing
+ is to assign a preference list of all the lookup table positions
+ to each destination.
+
+ Through this operation, The maglev hashing gives an almost equal
+ share of the lookup table to each of the destinations and provides
+ minimal disruption by using the lookup table. When the set of
+ destinations changes, a connection will likely be sent to the same
+ destination as it was before.
+
+ If you want to compile it in kernel, say Y. To compile it as a
+ module, choose M here. If unsure, say N.
+
config IP_VS_SED
tristate "shortest expected delay scheduling"
---help---
@@ -266,6 +285,24 @@ config IP_VS_SH_TAB_BITS
needs to be large enough to effectively fit all the destinations
multiplied by their respective weights.
+comment 'IPVS MH scheduler'
+
+config IP_VS_MH_TAB_INDEX
+ int "IPVS maglev hashing table index of size (the prime numbers)"
+ range 8 17
+ default 12
+ ---help---
+ The maglev hashing scheduler maps source IPs to destinations
+ stored in a hash table. This table is assigned by a preference
+ list of the positions to each destination until all slots in
+ the table are filled. The index determines the prime for size of
+ the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749,
+ 65521 or 131071. When using weights to allow destinations to
+ receive more connections, the table is assigned an amount
+ proportional to the weights specified. The table needs to be large
+ enough to effectively fit all the destinations multiplied by their
+ respective weights.
+
comment 'IPVS application helper'
config IP_VS_FTP
diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile
index c552993fa4b9..bfce2677fda2 100644
--- a/net/netfilter/ipvs/Makefile
+++ b/net/netfilter/ipvs/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_IP_VS_LBLC) += ip_vs_lblc.o
obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o
obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o
obj-$(CONFIG_IP_VS_SH) += ip_vs_sh.o
+obj-$(CONFIG_IP_VS_MH) += ip_vs_mh.o
obj-$(CONFIG_IP_VS_SED) += ip_vs_sed.o
obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o
--
2.11.0
^ permalink raw reply related
* [PATCH 03/51] netfilter: ipvs: Add Maglev hashing scheduler
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=UTF-8, Size: 15318 bytes --]
From: Inju Song <inju.song@navercorp.com>
Implements the Google's Maglev hashing algorithm as a IPVS scheduler.
Basically it provides consistent hashing but offers some special
features about disruption and load balancing.
1)Â minimal disruption: when the set of destinations changes,
a connection will likely be sent to the same destination
as it was before.
2)Â load balancing: each destination will receive an almost
equal number of connections.
Seel also for detail: [3.4 Consistent Hasing] in
https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-eisenbud.pdf
Signed-off-by: Inju Song <inju.song@navercorp.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_mh.c | 540 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 540 insertions(+)
create mode 100644 net/netfilter/ipvs/ip_vs_mh.c
diff --git a/net/netfilter/ipvs/ip_vs_mh.c b/net/netfilter/ipvs/ip_vs_mh.c
new file mode 100644
index 000000000000..0f795b186eb3
--- /dev/null
+++ b/net/netfilter/ipvs/ip_vs_mh.c
@@ -0,0 +1,540 @@
+// SPDX-License-Identifier: GPL-2.0
+/* IPVS: Maglev Hashing scheduling module
+ *
+ * Authors: Inju Song <inju.song@navercorp.com>
+ *
+ */
+
+/* The mh algorithm is to assign a preference list of all the lookup
+ * table positions to each destination and populate the table with
+ * the most-preferred position of destinations. Then it is to select
+ * destination with the hash key of source IP address through looking
+ * up a the lookup table.
+ *
+ * The algorithm is detailed in:
+ * [3.4 Consistent Hasing]
+https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-eisenbud.pdf
+ *
+ */
+
+#define KMSG_COMPONENT "IPVS"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/ip.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+
+#include <net/ip_vs.h>
+
+#include <linux/siphash.h>
+#include <linux/bitops.h>
+#include <linux/gcd.h>
+
+#define IP_VS_SVC_F_SCHED_MH_FALLBACK IP_VS_SVC_F_SCHED1 /* MH fallback */
+#define IP_VS_SVC_F_SCHED_MH_PORT IP_VS_SVC_F_SCHED2 /* MH use port */
+
+struct ip_vs_mh_lookup {
+ struct ip_vs_dest __rcu *dest; /* real server (cache) */
+};
+
+struct ip_vs_mh_dest_setup {
+ unsigned int offset; /* starting offset */
+ unsigned int skip; /* skip */
+ unsigned int perm; /* next_offset */
+ int turns; /* weight / gcd() and rshift */
+};
+
+/* Available prime numbers for MH table */
+static int primes[] = {251, 509, 1021, 2039, 4093,
+ 8191, 16381, 32749, 65521, 131071};
+
+/* For IPVS MH entry hash table */
+#ifndef CONFIG_IP_VS_MH_TAB_INDEX
+#define CONFIG_IP_VS_MH_TAB_INDEX 12
+#endif
+#define IP_VS_MH_TAB_BITS (CONFIG_IP_VS_MH_TAB_INDEX / 2)
+#define IP_VS_MH_TAB_INDEX (CONFIG_IP_VS_MH_TAB_INDEX - 8)
+#define IP_VS_MH_TAB_SIZE primes[IP_VS_MH_TAB_INDEX]
+
+struct ip_vs_mh_state {
+ struct rcu_head rcu_head;
+ struct ip_vs_mh_lookup *lookup;
+ struct ip_vs_mh_dest_setup *dest_setup;
+ hsiphash_key_t hash1, hash2;
+ int gcd;
+ int rshift;
+};
+
+static inline void generate_hash_secret(hsiphash_key_t *hash1,
+ hsiphash_key_t *hash2)
+{
+ hash1->key[0] = 2654435761UL;
+ hash1->key[1] = 2654435761UL;
+
+ hash2->key[0] = 2654446892UL;
+ hash2->key[1] = 2654446892UL;
+}
+
+/* Helper function to determine if server is unavailable */
+static inline bool is_unavailable(struct ip_vs_dest *dest)
+{
+ return atomic_read(&dest->weight) <= 0 ||
+ dest->flags & IP_VS_DEST_F_OVERLOAD;
+}
+
+/* Returns hash value for IPVS MH entry */
+static inline unsigned int
+ip_vs_mh_hashkey(int af, const union nf_inet_addr *addr,
+ __be16 port, hsiphash_key_t *key, unsigned int offset)
+{
+ unsigned int v;
+ __be32 addr_fold = addr->ip;
+
+#ifdef CONFIG_IP_VS_IPV6
+ if (af == AF_INET6)
+ addr_fold = addr->ip6[0] ^ addr->ip6[1] ^
+ addr->ip6[2] ^ addr->ip6[3];
+#endif
+ v = (offset + ntohs(port) + ntohl(addr_fold));
+ return hsiphash(&v, sizeof(v), key);
+}
+
+/* Reset all the hash buckets of the specified table. */
+static void ip_vs_mh_reset(struct ip_vs_mh_state *s)
+{
+ int i;
+ struct ip_vs_mh_lookup *l;
+ struct ip_vs_dest *dest;
+
+ l = &s->lookup[0];
+ for (i = 0; i < IP_VS_MH_TAB_SIZE; i++) {
+ dest = rcu_dereference_protected(l->dest, 1);
+ if (dest) {
+ ip_vs_dest_put(dest);
+ RCU_INIT_POINTER(l->dest, NULL);
+ }
+ l++;
+ }
+}
+
+static int ip_vs_mh_permutate(struct ip_vs_mh_state *s,
+ struct ip_vs_service *svc)
+{
+ struct list_head *p;
+ struct ip_vs_mh_dest_setup *ds;
+ struct ip_vs_dest *dest;
+ int lw;
+
+ /* If gcd is smaller then 1, number of dests or
+ * all last_weight of dests are zero. So, skip
+ * permutation for the dests.
+ */
+ if (s->gcd < 1)
+ return 0;
+
+ /* Set dest_setup for the dests permutation */
+ p = &svc->destinations;
+ ds = &s->dest_setup[0];
+ while ((p = p->next) != &svc->destinations) {
+ dest = list_entry(p, struct ip_vs_dest, n_list);
+
+ ds->offset = ip_vs_mh_hashkey(svc->af, &dest->addr,
+ dest->port, &s->hash1, 0) %
+ IP_VS_MH_TAB_SIZE;
+ ds->skip = ip_vs_mh_hashkey(svc->af, &dest->addr,
+ dest->port, &s->hash2, 0) %
+ (IP_VS_MH_TAB_SIZE - 1) + 1;
+ ds->perm = ds->offset;
+
+ lw = atomic_read(&dest->last_weight);
+ ds->turns = ((lw / s->gcd) >> s->rshift) ? : (lw != 0);
+ ds++;
+ }
+
+ return 0;
+}
+
+static int ip_vs_mh_populate(struct ip_vs_mh_state *s,
+ struct ip_vs_service *svc)
+{
+ int n, c, dt_count;
+ unsigned long *table;
+ struct list_head *p;
+ struct ip_vs_mh_dest_setup *ds;
+ struct ip_vs_dest *dest, *new_dest;
+
+ /* If gcd is smaller then 1, number of dests or
+ * all last_weight of dests are zero. So, skip
+ * the population for the dests and reset lookup table.
+ */
+ if (s->gcd < 1) {
+ ip_vs_mh_reset(s);
+ return 0;
+ }
+
+ table = kcalloc(BITS_TO_LONGS(IP_VS_MH_TAB_SIZE),
+ sizeof(unsigned long), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ p = &svc->destinations;
+ n = 0;
+ dt_count = 0;
+ while (n < IP_VS_MH_TAB_SIZE) {
+ if (p == &svc->destinations)
+ p = p->next;
+
+ ds = &s->dest_setup[0];
+ while (p != &svc->destinations) {
+ /* Ignore added server with zero weight */
+ if (ds->turns < 1) {
+ p = p->next;
+ ds++;
+ continue;
+ }
+
+ c = ds->perm;
+ while (test_bit(c, table)) {
+ /* Add skip, mod IP_VS_MH_TAB_SIZE */
+ ds->perm += ds->skip;
+ if (ds->perm >= IP_VS_MH_TAB_SIZE)
+ ds->perm -= IP_VS_MH_TAB_SIZE;
+ c = ds->perm;
+ }
+
+ __set_bit(c, table);
+
+ dest = rcu_dereference_protected(s->lookup[c].dest, 1);
+ new_dest = list_entry(p, struct ip_vs_dest, n_list);
+ if (dest != new_dest) {
+ if (dest)
+ ip_vs_dest_put(dest);
+ ip_vs_dest_hold(new_dest);
+ RCU_INIT_POINTER(s->lookup[c].dest, new_dest);
+ }
+
+ if (++n == IP_VS_MH_TAB_SIZE)
+ goto out;
+
+ if (++dt_count >= ds->turns) {
+ dt_count = 0;
+ p = p->next;
+ ds++;
+ }
+ }
+ }
+
+out:
+ kfree(table);
+ return 0;
+}
+
+/* Get ip_vs_dest associated with supplied parameters. */
+static inline struct ip_vs_dest *
+ip_vs_mh_get(struct ip_vs_service *svc, struct ip_vs_mh_state *s,
+ const union nf_inet_addr *addr, __be16 port)
+{
+ unsigned int hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1, 0)
+ % IP_VS_MH_TAB_SIZE;
+ struct ip_vs_dest *dest = rcu_dereference(s->lookup[hash].dest);
+
+ return (!dest || is_unavailable(dest)) ? NULL : dest;
+}
+
+/* As ip_vs_mh_get, but with fallback if selected server is unavailable */
+static inline struct ip_vs_dest *
+ip_vs_mh_get_fallback(struct ip_vs_service *svc, struct ip_vs_mh_state *s,
+ const union nf_inet_addr *addr, __be16 port)
+{
+ unsigned int offset, roffset;
+ unsigned int hash, ihash;
+ struct ip_vs_dest *dest;
+
+ /* First try the dest it's supposed to go to */
+ ihash = ip_vs_mh_hashkey(svc->af, addr, port,
+ &s->hash1, 0) % IP_VS_MH_TAB_SIZE;
+ dest = rcu_dereference(s->lookup[ihash].dest);
+ if (!dest)
+ return NULL;
+ if (!is_unavailable(dest))
+ return dest;
+
+ IP_VS_DBG_BUF(6, "MH: selected unavailable server %s:%u, reselecting",
+ IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port));
+
+ /* If the original dest is unavailable, loop around the table
+ * starting from ihash to find a new dest
+ */
+ for (offset = 0; offset < IP_VS_MH_TAB_SIZE; offset++) {
+ roffset = (offset + ihash) % IP_VS_MH_TAB_SIZE;
+ hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1,
+ roffset) % IP_VS_MH_TAB_SIZE;
+ dest = rcu_dereference(s->lookup[hash].dest);
+ if (!dest)
+ break;
+ if (!is_unavailable(dest))
+ return dest;
+ IP_VS_DBG_BUF(6,
+ "MH: selected unavailable server %s:%u (offset %u), reselecting",
+ IP_VS_DBG_ADDR(dest->af, &dest->addr),
+ ntohs(dest->port), roffset);
+ }
+
+ return NULL;
+}
+
+/* Assign all the hash buckets of the specified table with the service. */
+static int ip_vs_mh_reassign(struct ip_vs_mh_state *s,
+ struct ip_vs_service *svc)
+{
+ int ret;
+
+ if (svc->num_dests > IP_VS_MH_TAB_SIZE)
+ return -EINVAL;
+
+ if (svc->num_dests >= 1) {
+ s->dest_setup = kcalloc(svc->num_dests,
+ sizeof(struct ip_vs_mh_dest_setup),
+ GFP_KERNEL);
+ if (!s->dest_setup)
+ return -ENOMEM;
+ }
+
+ ip_vs_mh_permutate(s, svc);
+
+ ret = ip_vs_mh_populate(s, svc);
+ if (ret < 0)
+ goto out;
+
+ IP_VS_DBG_BUF(6, "MH: reassign lookup table of %s:%u\n",
+ IP_VS_DBG_ADDR(svc->af, &svc->addr),
+ ntohs(svc->port));
+
+out:
+ if (svc->num_dests >= 1) {
+ kfree(s->dest_setup);
+ s->dest_setup = NULL;
+ }
+ return ret;
+}
+
+static int ip_vs_mh_gcd_weight(struct ip_vs_service *svc)
+{
+ struct ip_vs_dest *dest;
+ int weight;
+ int g = 0;
+
+ list_for_each_entry(dest, &svc->destinations, n_list) {
+ weight = atomic_read(&dest->last_weight);
+ if (weight > 0) {
+ if (g > 0)
+ g = gcd(weight, g);
+ else
+ g = weight;
+ }
+ }
+ return g;
+}
+
+/* To avoid assigning huge weight for the MH table,
+ * calculate shift value with gcd.
+ */
+static int ip_vs_mh_shift_weight(struct ip_vs_service *svc, int gcd)
+{
+ struct ip_vs_dest *dest;
+ int new_weight, weight = 0;
+ int mw, shift;
+
+ /* If gcd is smaller then 1, number of dests or
+ * all last_weight of dests are zero. So, return
+ * shift value as zero.
+ */
+ if (gcd < 1)
+ return 0;
+
+ list_for_each_entry(dest, &svc->destinations, n_list) {
+ new_weight = atomic_read(&dest->last_weight);
+ if (new_weight > weight)
+ weight = new_weight;
+ }
+
+ /* Because gcd is greater than zero,
+ * the maximum weight and gcd are always greater than zero
+ */
+ mw = weight / gcd;
+
+ /* shift = occupied bits of weight/gcd - MH highest bits */
+ shift = fls(mw) - IP_VS_MH_TAB_BITS;
+ return (shift >= 0) ? shift : 0;
+}
+
+static void ip_vs_mh_state_free(struct rcu_head *head)
+{
+ struct ip_vs_mh_state *s;
+
+ s = container_of(head, struct ip_vs_mh_state, rcu_head);
+ kfree(s->lookup);
+ kfree(s);
+}
+
+static int ip_vs_mh_init_svc(struct ip_vs_service *svc)
+{
+ int ret;
+ struct ip_vs_mh_state *s;
+
+ /* Allocate the MH table for this service */
+ s = kzalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+
+ s->lookup = kcalloc(IP_VS_MH_TAB_SIZE, sizeof(struct ip_vs_mh_lookup),
+ GFP_KERNEL);
+ if (!s->lookup) {
+ kfree(s);
+ return -ENOMEM;
+ }
+
+ generate_hash_secret(&s->hash1, &s->hash2);
+ s->gcd = ip_vs_mh_gcd_weight(svc);
+ s->rshift = ip_vs_mh_shift_weight(svc, s->gcd);
+
+ IP_VS_DBG(6,
+ "MH lookup table (memory=%zdbytes) allocated for current service\n",
+ sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE);
+
+ /* Assign the lookup table with current dests */
+ ret = ip_vs_mh_reassign(s, svc);
+ if (ret < 0) {
+ ip_vs_mh_reset(s);
+ ip_vs_mh_state_free(&s->rcu_head);
+ return ret;
+ }
+
+ /* No more failures, attach state */
+ svc->sched_data = s;
+ return 0;
+}
+
+static void ip_vs_mh_done_svc(struct ip_vs_service *svc)
+{
+ struct ip_vs_mh_state *s = svc->sched_data;
+
+ /* Got to clean up lookup entry here */
+ ip_vs_mh_reset(s);
+
+ call_rcu(&s->rcu_head, ip_vs_mh_state_free);
+ IP_VS_DBG(6, "MH lookup table (memory=%zdbytes) released\n",
+ sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE);
+}
+
+static int ip_vs_mh_dest_changed(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest)
+{
+ struct ip_vs_mh_state *s = svc->sched_data;
+
+ s->gcd = ip_vs_mh_gcd_weight(svc);
+ s->rshift = ip_vs_mh_shift_weight(svc, s->gcd);
+
+ /* Assign the lookup table with the updated service */
+ return ip_vs_mh_reassign(s, svc);
+}
+
+/* Helper function to get port number */
+static inline __be16
+ip_vs_mh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph)
+{
+ __be16 _ports[2], *ports;
+
+ /* At this point we know that we have a valid packet of some kind.
+ * Because ICMP packets are only guaranteed to have the first 8
+ * bytes, let's just grab the ports. Fortunately they're in the
+ * same position for all three of the protocols we care about.
+ */
+ switch (iph->protocol) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_SCTP:
+ ports = skb_header_pointer(skb, iph->len, sizeof(_ports),
+ &_ports);
+ if (unlikely(!ports))
+ return 0;
+
+ if (likely(!ip_vs_iph_inverse(iph)))
+ return ports[0];
+ else
+ return ports[1];
+ default:
+ return 0;
+ }
+}
+
+/* Maglev Hashing scheduling */
+static struct ip_vs_dest *
+ip_vs_mh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
+{
+ struct ip_vs_dest *dest;
+ struct ip_vs_mh_state *s;
+ __be16 port = 0;
+ const union nf_inet_addr *hash_addr;
+
+ hash_addr = ip_vs_iph_inverse(iph) ? &iph->daddr : &iph->saddr;
+
+ IP_VS_DBG(6, "%s : Scheduling...\n", __func__);
+
+ if (svc->flags & IP_VS_SVC_F_SCHED_MH_PORT)
+ port = ip_vs_mh_get_port(skb, iph);
+
+ s = (struct ip_vs_mh_state *)svc->sched_data;
+
+ if (svc->flags & IP_VS_SVC_F_SCHED_MH_FALLBACK)
+ dest = ip_vs_mh_get_fallback(svc, s, hash_addr, port);
+ else
+ dest = ip_vs_mh_get(svc, s, hash_addr, port);
+
+ if (!dest) {
+ ip_vs_scheduler_err(svc, "no destination available");
+ return NULL;
+ }
+
+ IP_VS_DBG_BUF(6, "MH: source IP address %s:%u --> server %s:%u\n",
+ IP_VS_DBG_ADDR(svc->af, hash_addr),
+ ntohs(port),
+ IP_VS_DBG_ADDR(dest->af, &dest->addr),
+ ntohs(dest->port));
+
+ return dest;
+}
+
+/* IPVS MH Scheduler structure */
+static struct ip_vs_scheduler ip_vs_mh_scheduler = {
+ .name = "mh",
+ .refcnt = ATOMIC_INIT(0),
+ .module = THIS_MODULE,
+ .n_list = LIST_HEAD_INIT(ip_vs_mh_scheduler.n_list),
+ .init_service = ip_vs_mh_init_svc,
+ .done_service = ip_vs_mh_done_svc,
+ .add_dest = ip_vs_mh_dest_changed,
+ .del_dest = ip_vs_mh_dest_changed,
+ .upd_dest = ip_vs_mh_dest_changed,
+ .schedule = ip_vs_mh_schedule,
+};
+
+static int __init ip_vs_mh_init(void)
+{
+ return register_ip_vs_scheduler(&ip_vs_mh_scheduler);
+}
+
+static void __exit ip_vs_mh_cleanup(void)
+{
+ unregister_ip_vs_scheduler(&ip_vs_mh_scheduler);
+ rcu_barrier();
+}
+
+module_init(ip_vs_mh_init);
+module_exit(ip_vs_mh_cleanup);
+MODULE_DESCRIPTION("Maglev hashing ipvs scheduler");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Inju Song <inju.song@navercorp.com>");
--
2.11.0
^ permalink raw reply related
* [PATCH 02/51] netfilter: ipvs: Keep latest weight of destination
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Inju Song <inju.song@navercorp.com>
The hashing table in scheduler such as source hash or maglev hash
should ignore the changed weight to 0 and allow changing the weight
from/to non-0 values. So, struct ip_vs_dest needs to keep weight
with latest non-0 weight.
Signed-off-by: Inju Song <inju.song@navercorp.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 1 +
net/netfilter/ipvs/ip_vs_ctl.c | 4 ++++
2 files changed, 5 insertions(+)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index eb0bec043c96..0ac795b41ab8 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -668,6 +668,7 @@ struct ip_vs_dest {
volatile unsigned int flags; /* dest status flags */
atomic_t conn_flags; /* flags to copy to conn */
atomic_t weight; /* server weight */
+ atomic_t last_weight; /* server latest weight */
refcount_t refcnt; /* reference counter */
struct ip_vs_stats stats; /* statistics */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5ebde4b15810..b91bb70ece92 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -821,6 +821,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
if (add && udest->af != svc->af)
ipvs->mixed_address_family_dests++;
+ /* keep the last_weight with latest non-0 weight */
+ if (add || udest->weight != 0)
+ atomic_set(&dest->last_weight, udest->weight);
+
/* set the weight and the flags */
atomic_set(&dest->weight, udest->weight);
conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
--
2.11.0
^ permalink raw reply related
* [PATCH 01/51] netfilter: ipvs: Fix space before '[' error.
From: Pablo Neira Ayuso @ 2018-05-06 22:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <20180506224709.29100-1-pablo@netfilter.org>
From: Arvind Yadav <arvind.yadav.cs@gmail.com>
Fix checkpatch.pl error:
ERROR: space prohibited before open square bracket '['.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_proto_tcp.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index bcd9b7bde4ee..569631d2b2a1 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -436,7 +436,7 @@ static bool tcp_state_active(int state)
return tcp_state_active_table[state];
}
-static struct tcp_states_t tcp_states [] = {
+static struct tcp_states_t tcp_states[] = {
/* INPUT */
/* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},
@@ -459,7 +459,7 @@ static struct tcp_states_t tcp_states [] = {
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
};
-static struct tcp_states_t tcp_states_dos [] = {
+static struct tcp_states_t tcp_states_dos[] = {
/* INPUT */
/* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }},
--
2.11.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox